» Authors » Voot Tangkaratt

Voot Tangkaratt

Explore the profile of Voot Tangkaratt including associated specialties, affiliations and a list of published articles. Areas
Snapshot
Articles 7
Citations 4
Followers 0
Related Specialties
Co-Authors
Published In
Affiliations
Soon will be listed here.
Recent Articles
1.
Osa T, Tangkaratt V, Sugiyama M
Neural Netw . 2022 May; 152:90-104. PMID: 35523085
Reinforcement learning algorithms are typically limited to learning a single solution for a specified task, even though diverse solutions often exist. Recent studies showed that learning a set of diverse...
2.
Sasaki H, Tangkaratt V, Niu G, Sugiyama M
Neural Comput . 2017 Nov; 30(2):477-504. PMID: 29162006
Sufficient dimension reduction (SDR) is aimed at obtaining the low-rank projection matrix in the input space such that information about output data is maximally preserved. Among various approaches to SDR,...
3.
Tangkaratt V, Sasaki H, Sugiyama M
Neural Comput . 2017 Jun; 29(8):2076-2122. PMID: 28599116
A typical goal of linear-supervised dimension reduction is to find a low-dimensional subspace of the input space such that the projected input variables preserve maximal information about the output variables....
4.
Tangkaratt V, Morimoto J, Sugiyama M
Neural Netw . 2016 Sep; 84:1-16. PMID: 27639719
The goal of reinforcement learning is to learn an optimal policy which controls an agent to acquire the maximum cumulative reward. The model-based reinforcement learning approach learns a transition model...
5.
Tangkaratt V, Xie N, Sugiyama M
Neural Comput . 2014 Nov; 27(1):228-54. PMID: 25380340
Regression aims at estimating the conditional mean of output given input. However, regression is not informative enough if the conditional density is multimodal, heteroskedastic, and asymmetric. In such a case,...
6.
Tangkaratt V, Mori S, Zhao T, Morimoto J, Sugiyama M
Neural Netw . 2014 Jul; 57:128-40. PMID: 24995917
The goal of reinforcement learning (RL) is to let an agent learn an optimal control policy in an unknown environment so that future expected rewards are maximized. The model-free RL...
7.
Zhao T, Hachiya H, Tangkaratt V, Morimoto J, Sugiyama M
Neural Comput . 2013 Mar; 25(6):1512-47. PMID: 23517103
The policy gradient approach is a flexible and powerful reinforcement learning method particularly for problems with continuous actions such as robot control. A common challenge is how to reduce the...